diff options
| author | Tvrtko Ursulin <tvrtko.ursulin@intel.com> | 2019-05-22 16:57:14 +0100 |
|---|---|---|
| committer | Tvrtko Ursulin <tvrtko.ursulin@intel.com> | 2019-05-23 15:12:13 +0100 |
| commit | dd3e739742be37867c2f79facbf72129ef7315d3 (patch) | |
| tree | 8a402cdd87ae4855fedd09e2c17428c56ff69c67 /benchmarks/wsim | |
| parent | 11b65046bd5151701dd7dc3bdc562f6ab3f34a78 (diff) | |
gem_wsim: Per context SSEU control
A new workload command ('S') is added which allows per context slice
(re-)configuration.
v2:
* Only query device SSEU on first use. (Chris)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Diffstat (limited to 'benchmarks/wsim')
| -rw-r--r-- | benchmarks/wsim/README | 23 |
1 files changed, 22 insertions, 1 deletions
diff --git a/benchmarks/wsim/README b/benchmarks/wsim/README index 497d5cad..9f770217 100644 --- a/benchmarks/wsim/README +++ b/benchmarks/wsim/README @@ -5,7 +5,7 @@ ctx.engine.duration_us.dependency.wait,... <uint>.<str>.<uint>[-<uint>]|*.<int <= 0>[/<int <= 0>][...].<0|1>,... B.<uint> M.<uint>.<str>[|<str>]... -P|X.<uint>.<int> +P|S|X.<uint>.<int> d|p|s|t|q|a|T.<int>,... b.<uint>.<str>[|<str>].<str> f @@ -30,6 +30,7 @@ Additional workload steps are also supported: 'b' - Set up engine bonds. 'M' - Set up engine map. 'P' - Context priority. + 'S' - Context SSEU configuration. 'T' - Terminate an infinite batch. 'X' - Context preemption control. @@ -254,3 +255,23 @@ then look like: 1.DEFAULT.1000.f-1.0 2.DEFAULT.1000.s-1.0 a.-3 + +Context SSEU configuration +-------------------------- + + S.1.1 + 1.RCS.1000.0.0 + S.2.-1 + 2.RCS.1000.0.0 + +Context 1 is configured to run with one enabled slice (slice mask 1) and a batch +is sumitted against it. Context 2 is configured to run with all slices (this is +the default so the command could also be omitted) and a batch submitted against +it. + +This shows the dynamic SSEU reconfiguration cost beween two contexts competing +for the render engine. + +Slice mask of -1 has a special meaning of "all slices". Otherwise any integer +can be specifying as the slice mask, but beware any apart from 1 and -1 can make +the workload not portable between different GPUs. |